pstack-automate-me
Create or update a personal Pstack mode from repository-scoped history and explicit preferences.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,584 results
pstack-correct
Use in a Pstack task for recurring agent mistakes, structural prevention, or a rule-to-enforcer audit.
pstack-in-your-own-words
Use when a Pstack task needs the user goal and underlying problem restated before execution.
pstack-reflect
Use for Pstack reflection on corrections in the current conversation and reviewable improvements to source skills.
pstack-sharpen
Use when a Pstack task needs a stronger outcome or approach before execution while preserving an independent correctness check.
add-provider-models-to-pi
Add/adapt provider models to pi's models.json, including parameter fetching, three-layer reasoning synthesis, and capture.ts empirical verification and pinning.
cobo-agentic-wallet-dev
Create and manage agentic wallets with Cobo. Use for autonomous onchain operations via the caw CLI: token transfers, contract calls, pact creation and…
update-agent-skills
Update agent skills installed with the `skills` CLI. Use when asked to refresh installed skills, keep a project's skills current, or troubleshoot cases where…
sdlc-agentic-pipeline
Orchestrate a complete multi-agent SDLC pipeline powered by Huawei Cloud CodeArts Agent. 8 agents (PM, Backend, Frontend, Code Reviewer, Tester, DevOps,…
coder-templates
Creates and updates Coder Registry workspace templates with agent setup, infrastructure provisioning, and module consumption
composio-mcp
Use the Composio Connect MCP server to interact with 1000+ apps — GitHub, Slack, Notion, Gmail, Linear, Jira, and more. Composio manages auth, permissions, and…
task-loop
Scaffold a loop directory for automated agent task execution. Use when asked to "create a task loop", "set up a loop", "scaffold a loop directory", "prepare…
Master Agent Playbook
Philosophy, decision-making framework, and technical skills for delivering visual, interactive, and educational AI responses.
creativeclaw-seedream-5-pro
Apply Seedream 5 Pro prompting and reference techniques after Creative Claw selects that model. Use when the user explicitly requests Seedream 5 Pro, or when…
dispatch-opencode
Dispatch subagent tasks through opencode (https://opencode.ai) using the async .subagents/ lock-watch protocol. The agent writes a plan YAML, calls run-plan.sh…
memory-context
Retrieve relevant context from memory and preserve essential state. Use for episode retrieval, semantic search, or context compaction when window fills.
cross-fact-check
Claude + Gemini cross fact-check. Three parties—Opus itself, Gemini Flash, and Gemini Pro—independently check → extract issues → discuss → output a consensus report.
brainstorming-pm
Use when orchestrating multi-perspective brainstorming sessions requiring parallel agent execution, confidence-weighted synthesis, and optional workflow…
editor
Use when documents need prose improvement, CLAUDE.md style enforcement (prose over bullets, bridging transitions, complete sentences), or final polish before…
technical-pm
Use when coordinating multi-agent work with dependencies, parallel workstreams, or complex handoffs requiring milestone tracking
xceptionnet_gan_detector
The English introduction is being prepared.
llm-ops
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, advanced prompt engineering, LLM costs, quality evals, and AI architectures for...
b2a-agents
Builds agents that serve other AI agents (B2A). Use when designing x402 agents for agent-to-agent data sales, evaluating if a data niche is suitable for…
lucid-agent-editor
Edits and manages existing Lucid agents via the API. Covers three options: MCP tool with SIWE, SDK with wallet auth, or viem with custom signing. Use when…